RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents (Student Abstract)
Roman Sultimov, Mikhail Mozikov, Dmitrii Abramov, Mariia Kovalchuk, Maksim Malykh, Aleksandr Volkov, Ilya Makarov, Andrei Osiptsov
Abstract
Climate change is driving more frequent and severe disasters, putting people and infrastructure at risk. Protecting communities requires models that capture both natural disasters dynamics and how people behave under extreme conditions. This demo presents RESPOND, a multi-agent LLM-enhanced platform that jointly simulates natural hazards and human response. RESPOND couples high-fidelity flood AI forecasting an agent-based model of human behavior. LLM modules improve each agent decision-making, enabling context-aware reasoning over alerts, road closures, social signals, and changing water levels. The system simulates evacuation flows, resource seeking, and communication patterns producing actionable outputs for emergency management, urban planning, and policy. In the live demo one can run what-if or predicted scenarios, adjust assumptions, and observe emergent population behavior and risk hot spots in real time. By tightly coupling dynamic hazards with LLM-driven multi-agent behavior, RESPOND moves beyond fragmented tools and offers a practical, integrated platform for disaster preparedness and response.
BibTeX
@inproceedings{aaai2026_respondrealistic,
title = {RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents (Student Abstract)},
author = {Roman Sultimov and Mikhail Mozikov and Dmitrii Abramov and Mariia Kovalchuk and Maksim Malykh and Aleksandr Volkov and Ilya Makarov and Andrei Osiptsov and Yury Maximov},
booktitle = {AAAI 2026},
year = {2026}
}